summaryrefslogtreecommitdiffstats
path: root/fs/btrfs/extent_map.c
blob: b4c9a6aa118cd22f11246fcd45fc032fbccb79b2 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
// SPDX-License-Identifier: GPL-2.0

#include <linux/err.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include "messages.h"
#include "ctree.h"
#include "extent_map.h"
#include "compression.h"
#include "btrfs_inode.h"
#include "disk-io.h"


static struct kmem_cache *extent_map_cache;

int __init extent_map_init(void)
{
	extent_map_cache = kmem_cache_create("btrfs_extent_map",
					     sizeof(struct extent_map), 0, 0, NULL);
	if (!extent_map_cache)
		return -ENOMEM;
	return 0;
}

void __cold extent_map_exit(void)
{
	kmem_cache_destroy(extent_map_cache);
}

/*
 * Initialize the extent tree @tree.  Should be called for each new inode or
 * other user of the extent_map interface.
 */
void extent_map_tree_init(struct extent_map_tree *tree)
{
	tree->map = RB_ROOT_CACHED;
	INIT_LIST_HEAD(&tree->modified_extents);
	rwlock_init(&tree->lock);
}

/*
 * Allocate a new extent_map structure.  The new structure is returned with a
 * reference count of one and needs to be freed using free_extent_map()
 */
struct extent_map *alloc_extent_map(void)
{
	struct extent_map *em;
	em = kmem_cache_zalloc(extent_map_cache, GFP_NOFS);
	if (!em)
		return NULL;
	RB_CLEAR_NODE(&em->rb_node);
	refcount_set(&em->refs, 1);
	INIT_LIST_HEAD(&em->list);
	return em;
}

/*
 * Drop the reference out on @em by one and free the structure if the reference
 * count hits zero.
 */
void free_extent_map(struct extent_map *em)
{
	if (!em)
		return;
	if (refcount_dec_and_test(&em->refs)) {
		WARN_ON(extent_map_in_tree(em));
		WARN_ON(!list_empty(&em->list));
		kmem_cache_free(extent_map_cache, em);
	}
}

/* Do the math around the end of an extent, handling wrapping. */
static u64 range_end(u64 start, u64 len)
{
	if (start + len < start)
		return (u64)-1;
	return start + len;
}

static void dec_evictable_extent_maps(struct btrfs_inode *inode)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;

	if (!btrfs_is_testing(fs_info) && is_fstree(btrfs_root_id(inode->root)))
		percpu_counter_dec(&fs_info->evictable_extent_maps);
}

static int tree_insert(struct rb_root_cached *root, struct extent_map *em)
{
	struct rb_node **p = &root->rb_root.rb_node;
	struct rb_node *parent = NULL;
	struct extent_map *entry = NULL;
	struct rb_node *orig_parent = NULL;
	u64 end = range_end(em->start, em->len);
	bool leftmost = true;

	while (*p) {
		parent = *p;
		entry = rb_entry(parent, struct extent_map, rb_node);

		if (em->start < entry->start) {
			p = &(*p)->rb_left;
		} else if (em->start >= extent_map_end(entry)) {
			p = &(*p)->rb_right;
			leftmost = false;
		} else {
			return -EEXIST;
		}
	}

	orig_parent = parent;
	while (parent && em->start >= extent_map_end(entry)) {
		parent = rb_next(parent);
		entry = rb_entry(parent, struct extent_map, rb_node);
	}
	if (parent)
		if (end > entry->start && em->start < extent_map_end(entry))
			return -EEXIST;

	parent = orig_parent;
	entry = rb_entry(parent, struct extent_map, rb_node);
	while (parent && em->start < entry->start) {
		parent = rb_prev(parent);
		entry = rb_entry(parent, struct extent_map, rb_node);
	}
	if (parent)
		if (end > entry->start && em->start < extent_map_end(entry))
			return -EEXIST;

	rb_link_node(&em->rb_node, orig_parent, p);
	rb_insert_color_cached(&em->rb_node, root, leftmost);
	return 0;
}

/*
 * Search through the tree for an extent_map with a given offset.  If it can't
 * be found, try to find some neighboring extents
 */
static struct rb_node *__tree_search(struct rb_root *root, u64 offset,
				     struct rb_node **prev_or_next_ret)
{
	struct rb_node *n = root->rb_node;
	struct rb_node *prev = NULL;
	struct rb_node *orig_prev = NULL;
	struct extent_map *entry;
	struct extent_map *prev_entry = NULL;

	ASSERT(prev_or_next_ret);

	while (n) {
		entry = rb_entry(n, struct extent_map, rb_node);
		prev = n;
		prev_entry = entry;

		if (offset < entry->start)
			n = n->rb_left;
		else if (offset >= extent_map_end(entry))
			n = n->rb_right;
		else
			return n;
	}

	orig_prev = prev;
	while (prev && offset >= extent_map_end(prev_entry)) {
		prev = rb_next(prev);
		prev_entry = rb_entry(prev, struct extent_map, rb_node);
	}

	/*
	 * Previous extent map found, return as in this case the caller does not
	 * care about the next one.
	 */
	if (prev) {
		*prev_or_next_ret = prev;
		return NULL;
	}

	prev = orig_prev;
	prev_entry = rb_entry(prev, struct extent_map, rb_node);
	while (prev && offset < prev_entry->start) {
		prev = rb_prev(prev);
		prev_entry = rb_entry(prev, struct extent_map, rb_node);
	}
	*prev_or_next_ret = prev;

	return NULL;
}

static inline u64 extent_map_block_end(const struct extent_map *em)
{
	if (em->block_start + em->block_len < em->block_start)
		return (u64)-1;
	return em->block_start + em->block_len;
}

static bool can_merge_extent_map(const struct extent_map *em)
{
	if (em->flags & EXTENT_FLAG_PINNED)
		return false;

	/* Don't merge compressed extents, we need to know their actual size. */
	if (extent_map_is_compressed(em))
		return false;

	if (em->flags & EXTENT_FLAG_LOGGING)
		return false;

	/*
	 * We don't want to merge stuff that hasn't been written to the log yet
	 * since it may not reflect exactly what is on disk, and that would be
	 * bad.
	 */
	if (!list_empty(&em->list))
		return false;

	return true;
}

/* Check to see if two extent_map structs are adjacent and safe to merge. */
static bool mergeable_maps(const struct extent_map *prev, const struct extent_map *next)
{
	if (extent_map_end(prev) != next->start)
		return false;

	if (prev->flags != next->flags)
		return false;

	if (next->block_start < EXTENT_MAP_LAST_BYTE - 1)
		return next->block_start == extent_map_block_end(prev);

	/* HOLES and INLINE extents. */
	return next->block_start == prev->block_start;
}

static void try_merge_map(struct btrfs_inode *inode, struct extent_map *em)
{
	struct extent_map_tree *tree = &inode->extent_tree;
	struct extent_map *merge = NULL;
	struct rb_node *rb;

	/*
	 * We can't modify an extent map that is in the tree and that is being
	 * used by another task, as it can cause that other task to see it in
	 * inconsistent state during the merging. We always have 1 reference for
	 * the tree and 1 for this task (which is unpinning the extent map or
	 * clearing the logging flag), so anything > 2 means it's being used by
	 * other tasks too.
	 */
	if (refcount_read(&em->refs) > 2)
		return;

	if (!can_merge_extent_map(em))
		return;

	if (em->start != 0) {
		rb = rb_prev(&em->rb_node);
		if (rb)
			merge = rb_entry(rb, struct extent_map, rb_node);
		if (rb && can_merge_extent_map(merge) && mergeable_maps(merge, em)) {
			em->start = merge->start;
			em->orig_start = merge->orig_start;
			em->len += merge->len;
			em->block_len += merge->block_len;
			em->block_start = merge->block_start;
			em->generation = max(em->generation, merge->generation);
			em->flags |= EXTENT_FLAG_MERGED;

			rb_erase_cached(&merge->rb_node, &tree->map);
			RB_CLEAR_NODE(&merge->rb_node);
			free_extent_map(merge);
			dec_evictable_extent_maps(inode);
		}
	}

	rb = rb_next(&em->rb_node);
	if (rb)
		merge = rb_entry(rb, struct extent_map, rb_node);
	if (rb && can_merge_extent_map(merge) && mergeable_maps(em, merge)) {
		em->len += merge->len;
		em->block_len += merge->block_len;
		rb_erase_cached(&merge->rb_node, &tree->map);
		RB_CLEAR_NODE(&merge->rb_node);
		em->generation = max(em->generation, merge->generation);
		em->flags |= EXTENT_FLAG_MERGED;
		free_extent_map(merge);
		dec_evictable_extent_maps(inode);
	}
}

/*
 * Unpin an extent from the cache.
 *
 * @inode:	the inode from which we are unpinning an extent range
 * @start:	logical offset in the file
 * @len:	length of the extent
 * @gen:	generation that this extent has been modified in
 *
 * Called after an extent has been written to disk properly.  Set the generation
 * to the generation that actually added the file item to the inode so we know
 * we need to sync this extent when we call fsync().
 *
 * Returns: 0	     on success
 * 	    -ENOENT  when the extent is not found in the tree
 * 	    -EUCLEAN if the found extent does not match the expected start
 */
int unpin_extent_cache(struct btrfs_inode *inode, u64 start, u64 len, u64 gen)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	struct extent_map_tree *tree = &inode->extent_tree;
	int ret = 0;
	struct extent_map *em;

	write_lock(&tree->lock);
	em = lookup_extent_mapping(tree, start, len);

	if (WARN_ON(!em)) {
		btrfs_warn(fs_info,
"no extent map found for inode %llu (root %lld) when unpinning extent range [%llu, %llu), generation %llu",
			   btrfs_ino(inode), btrfs_root_id(inode->root),
			   start, start + len, gen);
		ret = -ENOENT;
		goto out;
	}

	if (WARN_ON(em->start != start)) {
		btrfs_warn(fs_info,
"found extent map for inode %llu (root %lld) with unexpected start offset %llu when unpinning extent range [%llu, %llu), generation %llu",
			   btrfs_ino(inode), btrfs_root_id(inode->root),
			   em->start, start, start + len, gen);
		ret = -EUCLEAN;
		goto out;
	}

	em->generation = gen;
	em->flags &= ~EXTENT_FLAG_PINNED;

	try_merge_map(inode, em);

out:
	write_unlock(&tree->lock);
	free_extent_map(em);
	return ret;

}

void clear_em_logging(struct btrfs_inode *inode, struct extent_map *em)
{
	lockdep_assert_held_write(&inode->extent_tree.lock);

	em->flags &= ~EXTENT_FLAG_LOGGING;
	if (extent_map_in_tree(em))
		try_merge_map(inode, em);
}

static inline void setup_extent_mapping(struct btrfs_inode *inode,
					struct extent_map *em,
					int modified)
{
	refcount_inc(&em->refs);

	ASSERT(list_empty(&em->list));

	if (modified)
		list_add(&em->list, &inode->extent_tree.modified_extents);
	else
		try_merge_map(inode, em);
}

/*
 * Add a new extent map to an inode's extent map tree.
 *
 * @inode:	the target inode
 * @em:		map to insert
 * @modified:	indicate whether the given @em should be added to the
 *	        modified list, which indicates the extent needs to be logged
 *
 * Insert @em into the @inode's extent map tree or perform a simple
 * forward/backward merge with existing mappings.  The extent_map struct passed
 * in will be inserted into the tree directly, with an additional reference
 * taken, or a reference dropped if the merge attempt was successful.
 */
static int add_extent_mapping(struct btrfs_inode *inode,
			      struct extent_map *em, int modified)
{
	struct extent_map_tree *tree = &inode->extent_tree;
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	int ret;

	lockdep_assert_held_write(&tree->lock);

	ret = tree_insert(&tree->map, em);
	if (ret)
		return ret;

	setup_extent_mapping(inode, em, modified);

	if (!btrfs_is_testing(fs_info) && is_fstree(btrfs_root_id(root)))
		percpu_counter_inc(&fs_info->evictable_extent_maps);

	return 0;
}

static struct extent_map *
__lookup_extent_mapping(struct extent_map_tree *tree,
			u64 start, u64 len, int strict)
{
	struct extent_map *em;
	struct rb_node *rb_node;
	struct rb_node *prev_or_next = NULL;
	u64 end = range_end(start, len);

	rb_node = __tree_search(&tree->map.rb_root, start, &prev_or_next);
	if (!rb_node) {
		if (prev_or_next)
			rb_node = prev_or_next;
		else
			return NULL;
	}

	em = rb_entry(rb_node, struct extent_map, rb_node);

	if (strict && !(end > em->start && start < extent_map_end(em)))
		return NULL;

	refcount_inc(&em->refs);
	return em;
}

/*
 * Lookup extent_map that intersects @start + @len range.
 *
 * @tree:	tree to lookup in
 * @start:	byte offset to start the search
 * @len:	length of the lookup range
 *
 * Find and return the first extent_map struct in @tree that intersects the
 * [start, len] range.  There may be additional objects in the tree that
 * intersect, so check the object returned carefully to make sure that no
 * additional lookups are needed.
 */
struct extent_map *lookup_extent_mapping(struct extent_map_tree *tree,
					 u64 start, u64 len)
{
	return __lookup_extent_mapping(tree, start, len, 1);
}

/*
 * Find a nearby extent map intersecting @start + @len (not an exact search).
 *
 * @tree:	tree to lookup in
 * @start:	byte offset to start the search
 * @len:	length of the lookup range
 *
 * Find and return the first extent_map struct in @tree that intersects the
 * [start, len] range.
 *
 * If one can't be found, any nearby extent may be returned
 */
struct extent_map *search_extent_mapping(struct extent_map_tree *tree,
					 u64 start, u64 len)
{
	return __lookup_extent_mapping(tree, start, len, 0);
}

/*
 * Remove an extent_map from its inode's extent tree.
 *
 * @inode:	the inode the extent map belongs to
 * @em:		extent map being removed
 *
 * Remove @em from the extent tree of @inode.  No reference counts are dropped,
 * and no checks are done to see if the range is in use.
 */
void remove_extent_mapping(struct btrfs_inode *inode, struct extent_map *em)
{
	struct extent_map_tree *tree = &inode->extent_tree;

	lockdep_assert_held_write(&tree->lock);

	WARN_ON(em->flags & EXTENT_FLAG_PINNED);
	rb_erase_cached(&em->rb_node, &tree->map);
	if (!(em->flags & EXTENT_FLAG_LOGGING))
		list_del_init(&em->list);
	RB_CLEAR_NODE(&em->rb_node);

	dec_evictable_extent_maps(inode);
}

static void replace_extent_mapping(struct btrfs_inode *inode,
				   struct extent_map *cur,
				   struct extent_map *new,
				   int modified)
{
	struct extent_map_tree *tree = &inode->extent_tree;

	lockdep_assert_held_write(&tree->lock);

	WARN_ON(cur->flags & EXTENT_FLAG_PINNED);
	ASSERT(extent_map_in_tree(cur));
	if (!(cur->flags & EXTENT_FLAG_LOGGING))
		list_del_init(&cur->list);
	rb_replace_node_cached(&cur->rb_node, &new->rb_node, &tree->map);
	RB_CLEAR_NODE(&cur->rb_node);

	setup_extent_mapping(inode, new, modified);
}

static struct extent_map *next_extent_map(const struct extent_map *em)
{
	struct rb_node *next;

	next = rb_next(&em->rb_node);
	if (!next)
		return NULL;
	return container_of(next, struct extent_map, rb_node);
}

static struct extent_map *prev_extent_map(struct extent_map *em)
{
	struct rb_node *prev;

	prev = rb_prev(&em->rb_node);
	if (!prev)
		return NULL;
	return container_of(prev, struct extent_map, rb_node);
}

/*
 * Helper for btrfs_get_extent.  Given an existing extent in the tree,
 * the existing extent is the nearest extent to map_start,
 * and an extent that you want to insert, deal with overlap and insert
 * the best fitted new extent into the tree.
 */
static noinline int merge_extent_mapping(struct btrfs_inode *inode,
					 struct extent_map *existing,
					 struct extent_map *em,
					 u64 map_start)
{
	struct extent_map *prev;
	struct extent_map *next;
	u64 start;
	u64 end;
	u64 start_diff;

	if (map_start < em->start || map_start >= extent_map_end(em))
		return -EINVAL;

	if (existing->start > map_start) {
		next = existing;
		prev = prev_extent_map(next);
	} else {
		prev = existing;
		next = next_extent_map(prev);
	}

	start = prev ? extent_map_end(prev) : em->start;
	start = max_t(u64, start, em->start);
	end = next ? next->start : extent_map_end(em);
	end = min_t(u64, end, extent_map_end(em));
	start_diff = start - em->start;
	em->start = start;
	em->len = end - start;
	if (em->block_start < EXTENT_MAP_LAST_BYTE &&
	    !extent_map_is_compressed(em)) {
		em->block_start += start_diff;
		em->block_len = em->len;
	}
	return add_extent_mapping(inode, em, 0);
}

/*
 * Add extent mapping into an inode's extent map tree.
 *
 * @inode:    target inode
 * @em_in:    extent we are inserting
 * @start:    start of the logical range btrfs_get_extent() is requesting
 * @len:      length of the logical range btrfs_get_extent() is requesting
 *
 * Note that @em_in's range may be different from [start, start+len),
 * but they must be overlapped.
 *
 * Insert @em_in into the inode's extent map tree. In case there is an
 * overlapping range, handle the -EEXIST by either:
 * a) Returning the existing extent in @em_in if @start is within the
 *    existing em.
 * b) Merge the existing extent with @em_in passed in.
 *
 * Return 0 on success, otherwise -EEXIST.
 *
 */
int btrfs_add_extent_mapping(struct btrfs_inode *inode,
			     struct extent_map **em_in, u64 start, u64 len)
{
	int ret;
	struct extent_map *em = *em_in;
	struct btrfs_fs_info *fs_info = inode->root->fs_info;

	/*
	 * Tree-checker should have rejected any inline extent with non-zero
	 * file offset. Here just do a sanity check.
	 */
	if (em->block_start == EXTENT_MAP_INLINE)
		ASSERT(em->start == 0);

	ret = add_extent_mapping(inode, em, 0);
	/* it is possible that someone inserted the extent into the tree
	 * while we had the lock dropped.  It is also possible that
	 * an overlapping map exists in the tree
	 */
	if (ret == -EEXIST) {
		struct extent_map *existing;

		existing = search_extent_mapping(&inode->extent_tree, start, len);

		trace_btrfs_handle_em_exist(fs_info, existing, em, start, len);

		/*
		 * existing will always be non-NULL, since there must be
		 * extent causing the -EEXIST.
		 */
		if (start >= existing->start &&
		    start < extent_map_end(existing)) {
			free_extent_map(em);
			*em_in = existing;
			ret = 0;
		} else {
			u64 orig_start = em->start;
			u64 orig_len = em->len;

			/*
			 * The existing extent map is the one nearest to
			 * the [start, start + len) range which overlaps
			 */
			ret = merge_extent_mapping(inode, existing, em, start);
			if (WARN_ON(ret)) {
				free_extent_map(em);
				*em_in = NULL;
				btrfs_warn(fs_info,
"extent map merge error existing [%llu, %llu) with em [%llu, %llu) start %llu",
					   existing->start, extent_map_end(existing),
					   orig_start, orig_start + orig_len, start);
			}
			free_extent_map(existing);
		}
	}

	ASSERT(ret == 0 || ret == -EEXIST);
	return ret;
}

/*
 * Drop all extent maps from a tree in the fastest possible way, rescheduling
 * if needed. This avoids searching the tree, from the root down to the first
 * extent map, before each deletion.
 */
static void drop_all_extent_maps_fast(struct btrfs_inode *inode)
{
	struct extent_map_tree *tree = &inode->extent_tree;

	write_lock(&tree->lock);
	while (!RB_EMPTY_ROOT(&tree->map.rb_root)) {
		struct extent_map *em;
		struct rb_node *node;

		node = rb_first_cached(&tree->map);
		em = rb_entry(node, struct extent_map, rb_node);
		em->flags &= ~(EXTENT_FLAG_PINNED | EXTENT_FLAG_LOGGING);
		remove_extent_mapping(inode, em);
		free_extent_map(em);
		cond_resched_rwlock_write(&tree->lock);
	}
	write_unlock(&tree->lock);
}

/*
 * Drop all extent maps in a given range.
 *
 * @inode:       The target inode.
 * @start:       Start offset of the range.
 * @end:         End offset of the range (inclusive value).
 * @skip_pinned: Indicate if pinned extent maps should be ignored or not.
 *
 * This drops all the extent maps that intersect the given range [@start, @end].
 * Extent maps that partially overlap the range and extend behind or beyond it,
 * are split.
 * The caller should have locked an appropriate file range in the inode's io
 * tree before calling this function.
 */
void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end,
				 bool skip_pinned)
{
	struct extent_map *split;
	struct extent_map *split2;
	struct extent_map *em;
	struct extent_map_tree *em_tree = &inode->extent_tree;
	u64 len = end - start + 1;

	WARN_ON(end < start);
	if (end == (u64)-1) {
		if (start == 0 && !skip_pinned) {
			drop_all_extent_maps_fast(inode);
			return;
		}
		len = (u64)-1;
	} else {
		/* Make end offset exclusive for use in the loop below. */
		end++;
	}

	/*
	 * It's ok if we fail to allocate the extent maps, see the comment near
	 * the bottom of the loop below. We only need two spare extent maps in
	 * the worst case, where the first extent map that intersects our range
	 * starts before the range and the last extent map that intersects our
	 * range ends after our range (and they might be the same extent map),
	 * because we need to split those two extent maps at the boundaries.
	 */
	split = alloc_extent_map();
	split2 = alloc_extent_map();

	write_lock(&em_tree->lock);
	em = lookup_extent_mapping(em_tree, start, len);

	while (em) {
		/* extent_map_end() returns exclusive value (last byte + 1). */
		const u64 em_end = extent_map_end(em);
		struct extent_map *next_em = NULL;
		u64 gen;
		unsigned long flags;
		bool modified;
		bool compressed;

		if (em_end < end) {
			next_em = next_extent_map(em);
			if (next_em) {
				if (next_em->start < end)
					refcount_inc(&next_em->refs);
				else
					next_em = NULL;
			}
		}

		if (skip_pinned && (em->flags & EXTENT_FLAG_PINNED)) {
			start = em_end;
			goto next;
		}

		flags = em->flags;
		/*
		 * In case we split the extent map, we want to preserve the
		 * EXTENT_FLAG_LOGGING flag on our extent map, but we don't want
		 * it on the new extent maps.
		 */
		em->flags &= ~(EXTENT_FLAG_PINNED | EXTENT_FLAG_LOGGING);
		modified = !list_empty(&em->list);

		/*
		 * The extent map does not cross our target range, so no need to
		 * split it, we can remove it directly.
		 */
		if (em->start >= start && em_end <= end)
			goto remove_em;

		gen = em->generation;
		compressed = extent_map_is_compressed(em);

		if (em->start < start) {
			if (!split) {
				split = split2;
				split2 = NULL;
				if (!split)
					goto remove_em;
			}
			split->start = em->start;
			split->len = start - em->start;

			if (em->block_start < EXTENT_MAP_LAST_BYTE) {
				split->orig_start = em->orig_start;
				split->block_start = em->block_start;

				if (compressed)
					split->block_len = em->block_len;
				else
					split->block_len = split->len;
				split->orig_block_len = max(split->block_len,
						em->orig_block_len);
				split->ram_bytes = em->ram_bytes;
			} else {
				split->orig_start = split->start;
				split->block_len = 0;
				split->block_start = em->block_start;
				split->orig_block_len = 0;
				split->ram_bytes = split->len;
			}

			split->generation = gen;
			split->flags = flags;
			replace_extent_mapping(inode, em, split, modified);
			free_extent_map(split);
			split = split2;
			split2 = NULL;
		}
		if (em_end > end) {
			if (!split) {
				split = split2;
				split2 = NULL;
				if (!split)
					goto remove_em;
			}
			split->start = end;
			split->len = em_end - end;
			split->block_start = em->block_start;
			split->flags = flags;
			split->generation = gen;

			if (em->block_start < EXTENT_MAP_LAST_BYTE) {
				split->orig_block_len = max(em->block_len,
						    em->orig_block_len);

				split->ram_bytes = em->ram_bytes;
				if (compressed) {
					split->block_len = em->block_len;
					split->orig_start = em->orig_start;
				} else {
					const u64 diff = end - em->start;

					split->block_len = split->len;
					split->block_start += diff;
					split->orig_start = em->orig_start;
				}
			} else {
				split->ram_bytes = split->len;
				split->orig_start = split->start;
				split->block_len = 0;
				split->orig_block_len = 0;
			}

			if (extent_map_in_tree(em)) {
				replace_extent_mapping(inode, em, split, modified);
			} else {
				int ret;

				ret = add_extent_mapping(inode, split, modified);
				/* Logic error, shouldn't happen. */
				ASSERT(ret == 0);
				if (WARN_ON(ret != 0) && modified)
					btrfs_set_inode_full_sync(inode);
			}
			free_extent_map(split);
			split = NULL;
		}
remove_em:
		if (extent_map_in_tree(em)) {
			/*
			 * If the extent map is still in the tree it means that
			 * either of the following is true:
			 *
			 * 1) It fits entirely in our range (doesn't end beyond
			 *    it or starts before it);
			 *
			 * 2) It starts before our range and/or ends after our
			 *    range, and we were not able to allocate the extent
			 *    maps for split operations, @split and @split2.
			 *
			 * If we are at case 2) then we just remove the entire
			 * extent map - this is fine since if anyone needs it to
			 * access the subranges outside our range, will just
			 * load it again from the subvolume tree's file extent
			 * item. However if the extent map was in the list of
			 * modified extents, then we must mark the inode for a
			 * full fsync, otherwise a fast fsync will miss this
			 * extent if it's new and needs to be logged.
			 */
			if ((em->start < start || em_end > end) && modified) {
				ASSERT(!split);
				btrfs_set_inode_full_sync(inode);
			}
			remove_extent_mapping(inode, em);
		}

		/*
		 * Once for the tree reference (we replaced or removed the
		 * extent map from the tree).
		 */
		free_extent_map(em);
next:
		/* Once for us (for our lookup reference). */
		free_extent_map(em);

		em = next_em;
	}

	write_unlock(&em_tree->lock);

	free_extent_map(split);
	free_extent_map(split2);
}

/*
 * Replace a range in the inode's extent map tree with a new extent map.
 *
 * @inode:      The target inode.
 * @new_em:     The new extent map to add to the inode's extent map tree.
 * @modified:   Indicate if the new extent map should be added to the list of
 *              modified extents (for fast fsync tracking).
 *
 * Drops all the extent maps in the inode's extent map tree that intersect the
 * range of the new extent map and adds the new extent map to the tree.
 * The caller should have locked an appropriate file range in the inode's io
 * tree before calling this function.
 */
int btrfs_replace_extent_map_range(struct btrfs_inode *inode,
				   struct extent_map *new_em,
				   bool modified)
{
	const u64 end = new_em->start + new_em->len - 1;
	struct extent_map_tree *tree = &inode->extent_tree;
	int ret;

	ASSERT(!extent_map_in_tree(new_em));

	/*
	 * The caller has locked an appropriate file range in the inode's io
	 * tree, but getting -EEXIST when adding the new extent map can still
	 * happen in case there are extents that partially cover the range, and
	 * this is due to two tasks operating on different parts of the extent.
	 * See commit 18e83ac75bfe67 ("Btrfs: fix unexpected EEXIST from
	 * btrfs_get_extent") for an example and details.
	 */
	do {
		btrfs_drop_extent_map_range(inode, new_em->start, end, false);
		write_lock(&tree->lock);
		ret = add_extent_mapping(inode, new_em, modified);
		write_unlock(&tree->lock);
	} while (ret == -EEXIST);

	return ret;
}

/*
 * Split off the first pre bytes from the extent_map at [start, start + len],
 * and set the block_start for it to new_logical.
 *
 * This function is used when an ordered_extent needs to be split.
 */
int split_extent_map(struct btrfs_inode *inode, u64 start, u64 len, u64 pre,
		     u64 new_logical)
{
	struct extent_map_tree *em_tree = &inode->extent_tree;
	struct extent_map *em;
	struct extent_map *split_pre = NULL;
	struct extent_map *split_mid = NULL;
	int ret = 0;
	unsigned long flags;

	ASSERT(pre != 0);
	ASSERT(pre < len);

	split_pre = alloc_extent_map();
	if (!split_pre)
		return -ENOMEM;
	split_mid = alloc_extent_map();
	if (!split_mid) {
		ret = -ENOMEM;
		goto out_free_pre;
	}

	lock_extent(&inode->io_tree, start, start + len - 1, NULL);
	write_lock(&em_tree->lock);
	em = lookup_extent_mapping(em_tree, start, len);
	if (!em) {
		ret = -EIO;
		goto out_unlock;
	}

	ASSERT(em->len == len);
	ASSERT(!extent_map_is_compressed(em));
	ASSERT(em->block_start < EXTENT_MAP_LAST_BYTE);
	ASSERT(em->flags & EXTENT_FLAG_PINNED);
	ASSERT(!(em->flags & EXTENT_FLAG_LOGGING));
	ASSERT(!list_empty(&em->list));

	flags = em->flags;
	em->flags &= ~EXTENT_FLAG_PINNED;

	/* First, replace the em with a new extent_map starting from * em->start */
	split_pre->start = em->start;
	split_pre->len = pre;
	split_pre->orig_start = split_pre->start;
	split_pre->block_start = new_logical;
	split_pre->block_len = split_pre->len;
	split_pre->orig_block_len = split_pre->block_len;
	split_pre->ram_bytes = split_pre->len;
	split_pre->flags = flags;
	split_pre->generation = em->generation;

	replace_extent_mapping(inode, em, split_pre, 1);

	/*
	 * Now we only have an extent_map at:
	 *     [em->start, em->start + pre]
	 */

	/* Insert the middle extent_map. */
	split_mid->start = em->start + pre;
	split_mid->len = em->len - pre;
	split_mid->orig_start = split_mid->start;
	split_mid->block_start = em->block_start + pre;
	split_mid->block_len = split_mid->len;
	split_mid->orig_block_len = split_mid->block_len;
	split_mid->ram_bytes = split_mid->len;
	split_mid->flags = flags;
	split_mid->generation = em->generation;
	add_extent_mapping(inode, split_mid, 1);

	/* Once for us */
	free_extent_map(em);
	/* Once for the tree */
	free_extent_map(em);

out_unlock:
	write_unlock(&em_tree->lock);
	unlock_extent(&inode->io_tree, start, start + len - 1, NULL);
	free_extent_map(split_mid);
out_free_pre:
	free_extent_map(split_pre);
	return ret;
}

struct btrfs_em_shrink_ctx {
	long nr_to_scan;
	long scanned;
	u64 last_ino;
	u64 last_root;
};

static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_ctx *ctx)
{
	const u64 cur_fs_gen = btrfs_get_fs_generation(inode->root->fs_info);
	struct extent_map_tree *tree = &inode->extent_tree;
	long nr_dropped = 0;
	struct rb_node *node;

	/*
	 * Take the mmap lock so that we serialize with the inode logging phase
	 * of fsync because we may need to set the full sync flag on the inode,
	 * in case we have to remove extent maps in the tree's list of modified
	 * extents. If we set the full sync flag in the inode while an fsync is
	 * in progress, we may risk missing new extents because before the flag
	 * is set, fsync decides to only wait for writeback to complete and then
	 * during inode logging it sees the flag set and uses the subvolume tree
	 * to find new extents, which may not be there yet because ordered
	 * extents haven't completed yet.
	 *
	 * We also do a try lock because otherwise we could deadlock. This is
	 * because the shrinker for this filesystem may be invoked while we are
	 * in a path that is holding the mmap lock in write mode. For example in
	 * a reflink operation while COWing an extent buffer, when allocating
	 * pages for a new extent buffer and under memory pressure, the shrinker
	 * may be invoked, and therefore we would deadlock by attempting to read
	 * lock the mmap lock while we are holding already a write lock on it.
	 */
	if (!down_read_trylock(&inode->i_mmap_lock))
		return 0;

	/*
	 * We want to be fast because we can be called from any path trying to
	 * allocate memory, so if the lock is busy we don't want to spend time
	 * waiting for it - either some task is about to do IO for the inode or
	 * we may have another task shrinking extent maps, here in this code, so
	 * skip this inode.
	 */
	if (!write_trylock(&tree->lock)) {
		up_read(&inode->i_mmap_lock);
		return 0;
	}

	node = rb_first_cached(&tree->map);
	while (node) {
		struct extent_map *em;

		em = rb_entry(node, struct extent_map, rb_node);
		node = rb_next(node);
		ctx->scanned++;

		if (em->flags & EXTENT_FLAG_PINNED)
			goto next;

		/*
		 * If the inode is in the list of modified extents (new) and its
		 * generation is the same (or is greater than) the current fs
		 * generation, it means it was not yet persisted so we have to
		 * set the full sync flag so that the next fsync will not miss
		 * it.
		 */
		if (!list_empty(&em->list) && em->generation >= cur_fs_gen)
			btrfs_set_inode_full_sync(inode);

		remove_extent_mapping(inode, em);
		trace_btrfs_extent_map_shrinker_remove_em(inode, em);
		/* Drop the reference for the tree. */
		free_extent_map(em);
		nr_dropped++;
next:
		if (ctx->scanned >= ctx->nr_to_scan)
			break;

		/*
		 * Stop if we need to reschedule or there's contention on the
		 * lock. This is to avoid slowing other tasks trying to take the
		 * lock and because the shrinker might be called during a memory
		 * allocation path and we want to avoid taking a very long time
		 * and slowing down all sorts of tasks.
		 */
		if (need_resched() || rwlock_needbreak(&tree->lock))
			break;
	}
	write_unlock(&tree->lock);
	up_read(&inode->i_mmap_lock);

	return nr_dropped;
}

static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx *ctx)
{
	struct btrfs_inode *inode;
	long nr_dropped = 0;
	u64 min_ino = ctx->last_ino + 1;

	inode = btrfs_find_first_inode(root, min_ino);
	while (inode) {
		nr_dropped += btrfs_scan_inode(inode, ctx);

		min_ino = btrfs_ino(inode) + 1;
		ctx->last_ino = btrfs_ino(inode);
		btrfs_add_delayed_iput(inode);

		if (ctx->scanned >= ctx->nr_to_scan)
			break;

		/*
		 * We may be called from memory allocation paths, so we don't
		 * want to take too much time and slowdown tasks.
		 */
		if (need_resched())
			break;

		inode = btrfs_find_first_inode(root, min_ino);
	}

	if (inode) {
		/*
		 * There are still inodes in this root or we happened to process
		 * the last one and reached the scan limit. In either case set
		 * the current root to this one, so we'll resume from the next
		 * inode if there is one or we will find out this was the last
		 * one and move to the next root.
		 */
		ctx->last_root = btrfs_root_id(root);
	} else {
		/*
		 * No more inodes in this root, set extent_map_shrinker_last_ino to 0 so
		 * that when processing the next root we start from its first inode.
		 */
		ctx->last_ino = 0;
		ctx->last_root = btrfs_root_id(root) + 1;
	}

	return nr_dropped;
}

long btrfs_free_extent_maps(struct btrfs_fs_info *fs_info, long nr_to_scan)
{
	struct btrfs_em_shrink_ctx ctx;
	u64 start_root_id;
	u64 next_root_id;
	bool cycled = false;
	long nr_dropped = 0;

	ctx.scanned = 0;
	ctx.nr_to_scan = nr_to_scan;

	/*
	 * In case we have multiple tasks running this shrinker, make the next
	 * one start from the next inode in case it starts before we finish.
	 */
	spin_lock(&fs_info->extent_map_shrinker_lock);
	ctx.last_ino = fs_info->extent_map_shrinker_last_ino;
	fs_info->extent_map_shrinker_last_ino++;
	ctx.last_root = fs_info->extent_map_shrinker_last_root;
	spin_unlock(&fs_info->extent_map_shrinker_lock);

	start_root_id = ctx.last_root;
	next_root_id = ctx.last_root;

	if (trace_btrfs_extent_map_shrinker_scan_enter_enabled()) {
		s64 nr = percpu_counter_sum_positive(&fs_info->evictable_extent_maps);

		trace_btrfs_extent_map_shrinker_scan_enter(fs_info, nr_to_scan,
							   nr, ctx.last_root,
							   ctx.last_ino);
	}

	/*
	 * We may be called from memory allocation paths, so we don't want to
	 * take too much time and slowdown tasks, so stop if we need reschedule.
	 */
	while (ctx.scanned < ctx.nr_to_scan && !need_resched()) {
		struct btrfs_root *root;
		unsigned long count;

		spin_lock(&fs_info->fs_roots_radix_lock);
		count = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
					       (void **)&root,
					       (unsigned long)next_root_id, 1);
		if (count == 0) {
			spin_unlock(&fs_info->fs_roots_radix_lock);
			if (start_root_id > 0 && !cycled) {
				next_root_id = 0;
				ctx.last_root = 0;
				ctx.last_ino = 0;
				cycled = true;
				continue;
			}
			break;
		}
		next_root_id = btrfs_root_id(root) + 1;
		root = btrfs_grab_root(root);
		spin_unlock(&fs_info->fs_roots_radix_lock);

		if (!root)
			continue;

		if (is_fstree(btrfs_root_id(root)))
			nr_dropped += btrfs_scan_root(root, &ctx);

		btrfs_put_root(root);
	}

	/*
	 * In case of multiple tasks running this extent map shrinking code this
	 * isn't perfect but it's simple and silences things like KCSAN. It's
	 * not possible to know which task made more progress because we can
	 * cycle back to the first root and first inode if it's not the first
	 * time the shrinker ran, see the above logic. Also a task that started
	 * later may finish ealier than another task and made less progress. So
	 * make this simple and update to the progress of the last task that
	 * finished, with the occasional possiblity of having two consecutive
	 * runs of the shrinker process the same inodes.
	 */
	spin_lock(&fs_info->extent_map_shrinker_lock);
	fs_info->extent_map_shrinker_last_ino = ctx.last_ino;
	fs_info->extent_map_shrinker_last_root = ctx.last_root;
	spin_unlock(&fs_info->extent_map_shrinker_lock);

	if (trace_btrfs_extent_map_shrinker_scan_exit_enabled()) {
		s64 nr = percpu_counter_sum_positive(&fs_info->evictable_extent_maps);

		trace_btrfs_extent_map_shrinker_scan_exit(fs_info, nr_dropped,
							  nr, ctx.last_root,
							  ctx.last_ino);
	}

	return nr_dropped;
}